265 datasets found

The BOP Challenge 2022 is the fourth in a series of public challenges that are part of the BOP1 project aiming to continuously report the state of the art in 6D object pose...

Multi-label image recognition is a practical and challenging task compared to single-label image classification.

The dataset used in the paper is a multi-view clustering dataset, which contains 6 views of 30000 samples each. The dataset is used to evaluate the performance of the proposed...

The KITTI Vision Benchmark Suite is a dataset used for object detection and tracking in autonomous vehicles.

Custom dataset used to train and evaluate object detection models for detecting driver phone usage violations.

The Tiny YOLO dataset is a benchmark for object detection.

The dataset used in the paper is a publicly available dataset for object detection.

Scene segmentation in images is a fundamental yet challenging problem in visual content understanding, which is to learn a model to assign every image pixel to a categorical label.

The PASCAL VOC2007 dataset is a benchmark for object detection and image classification.

LVIS is a large-vocabulary object detection and instance segmentation dataset.

The dataset used in this paper is a collection of images and drone states, used for training and testing the Deep Optical Flow Dynamics and PixelMPC algorithm.

The RefCOCOg dataset is a reconstructed dataset of the MS-COCO dataset, containing 85,474 referring expressions for 54,822 objects in 26,711 images.

The dataset used in the paper is a benchmark for referring expression grounding, containing 142,210 referring expressions for 50,000 referents in 19,994 images.

The dataset used in the paper is Argoverse-HD.

The dataset used in the paper is Argoverse-HD, Cityscapes, and nuScenes.

The MSCOCO dataset is a large-scale image captioning dataset, containing 113,287 images with 5,000 validation images and 5,000 test images. The dataset is used for training and...

The ICCV dataset is a benchmark for learning deep object detectors from 3D models.

The Pets 2016 dataset is a benchmark for object detection in images.

The SafeSea dataset is created using the SafeSea method, involving the transformation of 300 calm ocean background images originally sourced from the 'SeaDroneSee' dataset.

The D2SA dataset is a class-specific amodal segmentation dataset, containing 2000 and 3600 original and artificially augmented images for training and validation.